MiDAS III (Mild® Decompression Alternative to Open Surgery): Vertos Mild Patient Evaluation Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for MiDAS III (Mild® Decompression Alternative to Open Surgery): Vertos Mild Patient Evaluation Study (NCT01315145), a non-randomized na study. The primary outcome is Percentage of Participants With a 2-point Improvement in Visual Analogue Scale.

2. Clinical Question

This is a question about the percentage of participants meeting a specified improvement threshold, rather than the average change in pain score. The threshold makes the primary outcome a binary response: each participant either meets the criterion or does not. The registry says that participants reporting 16-week outcomes are included in this analysis, but it does not state how many contributed to the endpoint in either group.

The comparison is observational and nonrandomized. Consequently, the groups cannot be assumed to be equivalent at the outset, and any difference in their outcomes would not by itself establish that treatment choice caused the difference. The registry record does not report a numerical response rate, a group comparison estimate, a confidence interval, or a significance test for the primary endpoint. The clinical question is defined, but its answer is not reported in the registry record.

3. Trial Design

The registry describes MiDAS III as a multicenter, prospective, observational clinical study comparing outcomes after percutaneous lumbar decompression or epidural steroid injection in patients with moderate to severe lumbar spinal stenosis exhibiting neurogenic claudication. The study is marked completed. Its reported enrollment is 138, its start is recorded as 2011-03, and its primary completion is recorded as 2014-05.

The design is listed as parallel, with nonrandomized allocation and no masking. Parallel means that participants were followed in treatment groups rather than through a crossover design. Nonrandomized allocation means the record does not describe assignment by chance. It does not report how treatment choice was made, whether participants or clinicians selected the treatment, or whether a particular clinical feature determined assignment. Those details are not reported in the registry record.

The named groups are Percutaneous Lumbar Decompression and Lumbar Epidural Steroid Injection. The first is described as percutaneous decompression using the mild® Device Kit; the second as injection of epidural steroids into the lumbar spine. Although both groups are part of the study, the record explicitly cautions that they are not a like-for-like control comparison because allocation was nonrandomized. Differences in baseline characteristics or other factors could therefore complicate interpretation of an unadjusted group contrast.

The registry lists the study phase as NA. It reports one outcome measure and zero analyses. Its primary outcome is the percentage of participants with at least a 2-point improvement in Visual Analogue Scale from baseline at 16 weeks. The analysis population is described as all participants who reported 16-week outcomes. The number with such outcomes in each group, the baseline comparability of the groups, the treatment-selection process, and the statistical analysis plan are not reported in the registry record.

The total enrollment should not be treated as the number analyzed for the primary endpoint or as the number in either group. The registry gives separate at-risk counts for adverse-event summaries, but those are safety denominators and do not establish the endpoint denominators. The sample-size justification, any planned interim analyses, and details of follow-up beyond the stated primary completion are not reported in the registry record.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Analysis population for the primary outcome, as defined in the registry: All participants who reported 16 week outcomes are included in this analysis.

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants With a 2-point Improvement in Visual Analogue Scale, measured over 16 weeks.

The primary endpoint is the percentage of participants with at least a 2-point improvement from baseline in the Visual Analogue Scale at 16 weeks. It translates each participant’s score change into a responder classification: participants meeting or exceeding the improvement threshold count as responders, while those who do not meet it do not. The group result would be the proportion of analyzed participants classified as responders.

This kind of endpoint is useful because it expresses the result as the fraction of participants reaching a prespecified level of change, rather than only describing an average score change. A threshold can make a group result easier to interpret as a response rate. However, it also discards information about the size of changes beyond the threshold and about changes that fall short of it. The threshold’s interpretation depends on how the scale and scoring were implemented; further details about the scale are not reported in the registry record.

The registry states that the endpoint uses participants who reported 16-week outcomes. It does not report the responder count or percentage in either group, the number of participants with available 16-week outcomes, or a comparison estimate. It also does not report uncertainty intervals or a statistical test. Thus the endpoint definition is available, but the observed response rates and their precision are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes the primary outcome as a percentage of participants who achieved a defined improvement threshold. This is a binary outcome at the participant level: each participant is classified as a responder or a non-responder. A group percentage expresses the number meeting the criterion relative to the group’s analyzed participants. The registry gives the definition but does not report the counts, percentages, or comparison analysis.

What does a response percentage represent?

For a binary outcome, the main descriptive quantity is the response proportion. A proportion is more informative when its denominator is clear, because the same response count can represent different proportions in groups of different sizes. Here, the analysis population is described as participants reporting 16-week outcomes, but the number with those outcomes in each group is not reported in the registry record. Enrollment of 138 cannot substitute for those analysis denominators.

A comparison of response proportions can be expressed in several ways, such as a difference between proportions or a ratio of proportions. These measures answer different questions and should be interpreted with their uncertainty intervals. This is general statistical explanation, not a description of an analysis reported for this study: the registry does not state which comparative measure or test was used, and it reports zero analyses.

Why does uncertainty matter?

A point estimate alone does not show how precisely a response rate or group contrast has been estimated. A confidence interval is a general method for expressing uncertainty around an estimate, under the assumptions of the chosen statistical procedure. A narrow interval indicates greater precision than a wide interval, but its meaning depends on the method and data. The registry record does not report a confidence interval for the primary endpoint, so its precision cannot be evaluated from the posted results.

A p-value is also a method-dependent summary, usually calculated against a null hypothesis. It does not measure the probability that a treatment is effective, and it does not indicate whether an observed difference is important. No p-value or null hypothesis for the primary endpoint is reported in the registry record. Without an estimate and an uncertainty measure, a reader cannot distinguish a small, precise contrast from a larger but imprecise one.

How does the design affect the comparison?

Random allocation is one way to balance measured and unmeasured characteristics between groups on average. This study is listed as nonrandomized, so that design protection is not available. General statistical methods may attempt to adjust for measured characteristics, but adjustment cannot automatically address unmeasured differences, and the registry does not report whether an adjusted analysis was performed or which covariates it would include. It also does not report treatment-selection criteria or baseline group characteristics.

No masking is reported. In general, lack of masking can influence how outcomes are reported or assessed, depending on the outcome and study procedures. The Visual Analogue Scale is a participant-reported measure in the endpoint description, but further details about administration and assessment procedures are not reported in the registry record. This design information is relevant context, not evidence that bias occurred.

What role does over-dispersion have?

Over-dispersion is a general concern when variability in observed data exceeds what a statistical model assumes. It matters because a model that understates variability can produce uncertainty intervals that are too narrow and tests that appear more decisive than warranted. This study’s primary endpoint is binary, but the registry does not report a model, a dispersion estimate, or an analysis that calls for an over-dispersion adjustment. It would not be appropriate to claim that over-dispersion was present or that a particular correction was used.

For a binary response, model choice can also depend on the estimand and the design. A simple unadjusted comparison describes the observed groups; an adjusted analysis conditions on selected measured characteristics and relies on assumptions about the model and the measured data. Neither approach removes the need to explain the analysis population, missing outcomes, and uncertainty. Those details are not reported for the primary outcome.

How should planning calculations be read?

General sample-size calculations are planning exercises, not observed power. The registry’s stated planning assumptions describe a two-sided significance level of 0.05, equal allocation, a normal approximation, and an effect defined as a stated fraction of the observed effect. Those are assumptions for a planning illustration, not evidence that the study was designed or analyzed that way. The record does not report its own sample-size justification. Any planning illustration should therefore be kept distinct from the study’s observed outcome and should not be presented as a retrospective measure of whether the study found a result.

The registry record does not provide the numerical primary outcome needed to judge the observed effect, nor does it report an analysis specification, adjustment strategy, or uncertainty estimate. Consequently, general statistical methods can explain how this kind of endpoint is often analyzed, but they cannot establish which method was used or reconstruct the missing result.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Percutaneous Lumbar Decompression", "Lumbar Epidural Steroid Injection")
n      <- c(114, 13)
events <- c(75, 6)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Percutaneous Lumbar Decompression  114  75  65.8  56.3  74.4  56.7  73.9  56.7  73.9
ARM  Lumbar Epidural Steroid Injection  13  6  46.2  19.2  74.9  23.2  70.9  23.0  71.1

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one outcome measure and zero analyses. It identifies the Visual Analogue Scale response at 16 weeks as the primary endpoint, but it does not report a statistical analysis of that endpoint. The record does not state whether other outcomes were planned, whether there were multiple time points or subgroups in the full protocol, or whether any multiplicity procedure was specified. These details are not reported in the registry record.

Multiplicity is a general statistical issue that arises when several hypotheses or outcomes are examined. With multiple opportunities to test a difference, the chance of at least one apparently notable result can increase unless the analysis plan accounts for the testing strategy. This is general context only; the available record does not establish that multiple tests were conducted or that a particular correction was needed.

The endpoint population is described as all participants who reported 16-week outcomes. The number of participants with those outcomes in each group, the amount and reasons for missing outcome data, and the handling of missing values are not reported in the registry record. It is therefore not possible to determine whether the analysis used only observed outcomes, imputed missing outcomes, or applied another approach.

Missing data can affect both precision and interpretation. If participants without a recorded outcome differ from those with one, a complete-outcome analysis may not represent all enrolled participants. This is a general concern, not a claim about what happened in this study. The registry gives no comparison of follow-up completeness between groups and no sensitivity analysis for missing outcomes.

The record also does not describe an intention-to-treat population or another analysis population beyond the participants reporting 16-week outcomes. No protocol-based analysis plan, interim analysis plan, or missing-data strategy is reported. These omissions make it difficult to assess whether the reported endpoint population and any analysis would align with a prespecified plan.

12. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: chest pain (6.2%), orthostasis (6.2%), subarachnoid hemorrhage (6.2%), subdural hematoma (6.2%), fever (hospitalized) (0.8%).

For serious adverse events, the registry records 4 among 122 at risk in the Percutaneous Lumbar Decompression group and 2 among 16 at risk in the Lumbar Epidural Steroid Injection group. For other adverse events, it records 8 among 122 at risk in the percutaneous decompression group and 0 among 16 at risk in the injection group. These are the recorded counts and denominators; no additional percentages need to be inferred from them.

The registry also lists serious-event terms with percentages: CHEST PAIN, 6.2%; ORTHOSTASIS, 6.2%; SUBARACHNOID HEMORRHAGE, 6.2%; SUBDURAL HEMATOMA, 6.2%; FEVER (HOSPITALIZED), 0.8%; and PROGRESSION OF SPINAL STENOSIS, 0.8%. The denominator and counting basis for these term-specific percentages are not reported in the registry record. The listed percentages should not be used to infer additional event counts.

These safety summaries do not establish that an event was caused by a procedure or injection. The registry record does not report deaths; the death entries are not populated. The unequal at-risk denominators and the absence of further details about event collection and follow-up also limit direct comparison. These counts describe what the registry records, not a causal assessment of comparative safety.

13. What the Result Does, and Does Not, Mean

The registry record defines a specific clinical question: whether participants in each nonrandomized group met a 2-point improvement threshold on the Visual Analogue Scale at 16 weeks. It also records the overall enrollment, study design, treatment descriptions, and safety counts. These details establish what the study set out to examine and offer context for interpreting its design.

The record does not report the primary response percentage for either group, an endpoint denominator, a group contrast, or a measure of uncertainty. It therefore does not show how frequently participants met the response threshold or how precisely the groups differed. The absence of a reported result is not evidence of no difference, just as it is not evidence of a difference.

Even if a group contrast were available, its interpretation would need to account for the observational, nonrandomized design. Participants were not assigned at random, and the record does not describe how treatment choice was made or whether baseline differences were adjusted for. A contrast between the recorded groups could reflect treatment differences, differences in the people receiving each treatment, or both. The record cautions that the groups are not a like-for-like control comparison.

The safety counts should be interpreted as registry-reported event counts with their stated at-risk denominators. They do not, by themselves, establish causation or provide a complete comparative safety analysis. The record does not report deaths, and further details about the term-specific percentages are not available.

In general, a statistical result is most informative when it includes an estimate, a clear analysis population, and an uncertainty measure, alongside design details and limitations. Those elements are not all available for the primary endpoint. The study status is completed, but completion does not fill in the missing endpoint results. The appropriate reading is that the registry record describes the intended endpoint and the study framework while leaving the numerical primary outcome unreported.

No medical conclusion about the relative effects of the procedures follows from the information recorded. This description concerns the reporting and statistical interpretation of the registry entry, not a recommendation about treatment.

14. Why This Trial Matters Statistically

This study is statistically instructive because it poses a direct comparison question while using a nonrandomized observational design. That distinction matters: a comparison between groups is not automatically a causal comparison. Readers need to consider how participants entered each group and whether relevant differences were measured and addressed. The registry record does not report those details and explicitly warns that the arms are not a like-for-like control comparison.

The endpoint also illustrates a common choice in clinical research: converting a continuous scale change into a responder outcome. A threshold can make the endpoint understandable as the percentage meeting a defined improvement criterion. At the same time, it hides variation in the amount of change within the responder and non-responder categories. Both the threshold definition and the denominator are essential to interpret a response rate. The registry provides the threshold and timing, but not the observed rates or analysis denominators.

Reporting matters as much as the endpoint definition. Without the numerical result, an uncertainty interval, and a clear account of missing outcomes, readers cannot judge the magnitude or precision of the primary comparison. Enrollment alone does not tell how many participants contributed a 16-week outcome, and safety denominators should not be substituted for endpoint denominators.

The entry also shows why registry summaries should be read as records of what is reported, rather than as complete statistical reports. The study is marked completed and has a defined primary endpoint, yet the registry lists zero analyses. The sample-size assumptions describe a planning illustration and should not be mistaken for evidence about observed power or a reported trial analysis. Separating design information, outcome definitions, analysis results, and planning exercises helps prevent stronger claims than the record supports.

15. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The most direct limitation for interpretation is that the primary endpoint result is not reported in the registry record. There is no group-specific responder percentage, responder count, endpoint denominator, between-group estimate, confidence interval, or p-value. As a result, the endpoint’s magnitude and precision cannot be assessed from this record.

The nonrandomized allocation limits causal interpretation. The registry does not report how participants came to receive one intervention rather than the other, what baseline characteristics were measured, whether the groups differed at baseline, or whether adjustment was used. The record itself warns that the groups are not a like-for-like control comparison. No conclusion about treatment causing an outcome difference can be drawn from the design description alone.

The stated endpoint population includes participants reporting outcomes at 16 weeks, but the record does not give group-specific follow-up counts, reasons for missing outcomes, or the method used to address missing data. It also does not report whether analysis populations beyond this endpoint group were defined. These omissions prevent assessment of follow-up completeness and potential selection effects.

The registry does not report a sample-size justification, the full statistical analysis plan, a multiplicity strategy, interim analyses, or methods for any adjusted comparison. It lists one outcome measure and zero analyses. The details needed to assess prespecification and analytical choices are therefore not available in the registry record.

For safety, the record supplies event counts and at-risk denominators, but the death entries are not populated and the basis for the term-specific percentages is not reported. The unequal denominators and limited event-collection details constrain interpretation of those summaries. These limitations do not establish that bias or incomplete reporting occurred; they describe what cannot be evaluated from the registry record.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: MiDAS III (Mild® Decompression Alternative to Open Surgery): Vertos Mild Patient Evaluation Study — NCT01315145.
• Registry record last updated 2015-08-31; status last verified 2015-08.
• Results first posted 2015-08-19.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

19. Record Summary

MiDAS III is a completed, multicenter, prospective, observational study of percutaneous lumbar decompression and lumbar epidural steroid injection in patients with moderate to severe lumbar spinal stenosis exhibiting neurogenic claudication. The registry records enrollment of 138, nonrandomized allocation, no masking, and a parallel model. The recorded start is 2011-03, and primary completion is 2014-05.

The primary outcome is the percentage of participants with at least a 2-point improvement from baseline in Visual Analogue Scale at 16 weeks, among participants reporting outcomes at that time. The registry does not report the endpoint results, analysis denominators, or statistical comparison. It records 4 serious adverse events among 122 at risk and 8 other adverse events among 122 at risk in the percutaneous decompression group; for the injection group, it records 2 serious adverse events among 16 at risk and 0 other adverse events among 16 at risk. Deaths are not reported. Interpretation is limited by nonrandomized allocation, missing endpoint results, and unreported analysis and missing-data details.